The artificial intelligence (AI) has proven useful in reading medical images and has even been shown to pass the licensing exam for doctors.
Now, a new AI tool has demonstrated the ability to read medical notes and accurately anticipate patients’ risk of death, their readmission to hospital, and other outcomes important to their care.
Designed by a team from Grossman School of Medicine of the NYUthe program is currently used in all hospitals affiliated with this university in New York, with the hope that it will become standard in healthcare.
The study on its predictive value was published this Wednesday in the journal Nature.
The main author, Eric Oermannneurosurgeon of the NYU and computer scientist, told AFP that while predictive models without AI they’ve been around medicine for several years, they’ve been rarely used in practice because the data you need requires cumbersome rearranging and formatting.
However, “one thing that is common in medicine everywhere is that doctors write notes about what they see in the clinic, what they have discussed with patients“, said.
“So our basic insight was: Can we start with medical notes as a data source and then build predictive models on top of them?”.
The huge language model called NYUTron was trained with millions of medical notes extracted from the medical records of 387,000 people who received medical care in hospitals NYU Langone between January 2011 and May 2020.
These records included those written by doctors, patient progress notes, radiology reports, and discharge instructions, totaling 4.1 billion words.
One of the key challenges for the program was interpreting the natural language that doctors write, which varies widely among individuals, including by the abbreviations each uses.
By looking at records of what they got, the researchers were able to calculate how often the program’s predictions were accurate.
They also tested the tool in live environments, training it on records from a hospital in Manhattan and then seeing how it performed in one in Brooklyn, with different patient demographics.
Overall, NYUTron identified a staggering 95% of people who died in the hospital before being discharged, and 80% of patients who would be readmitted within 30 days.
The tool outperformed most of the doctors’ predictions, and also outperformed current models that do not use AI.
However, to the surprise of the team, “the most experienced of the doctors, who is in fact very famous, had a superhuman performance, better than the modelOermann said.
“The sweet spot between technology and medicine is not that medicine must always necessarily deliver superhuman results, but rather that it really offers that starting point.”.
NYUTron also correctly estimated length of stay for 79% of patients, 89% of cases where patients were denied coverage by their insurance, and 89% of cases where the patient’s primary illness was accompanied by additional conditions.
AI will never be a substitute for the doctor-patient relationship, he says oermann. Instead, it will help “provide more information to physicians at the time of care so they can make more informed decisions”.
Ricardo is a renowned author and journalist, known for his exceptional writing on top-news stories. He currently works as a writer at the 247 News Agency, where he is known for his ability to deliver breaking news and insightful analysis on the most pressing issues of the day.